10001|76884|1995-06-24|1996-06-23
10001|76884|1995-06-24|1996-06-23
10001|75286|1993-06-24|1994-06-24
我的目标是删除dup值,输出像
10001|76884|1995-06-24|1996-06-23
10001|75286|1993-06-24|1994-06-24
我写了如下代码
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class charterSelDistRec {
public static class Map extends Mapper <LongWritable, Text, Text, Text> {
private String tableKey,tableValue;
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String splitarray[] = line.split("\\|",2);
tableKey = splitarray[0].trim();
tableValue = splitarray[1].trim();
context.write(new Text(tableKey), new Text(tableValue));
}
}
public static class Reduce extends Reducer <Text, Text, Text, Text> {
public void reduce(Text key, Iterator<Text> values, Context context)
throws IOException, InterruptedException {
String ColumnDelim="";
String tableOutValue=ColumnDelim+values;
context.write(new Text(key), new Text(tableOutValue));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf,"charterSelDistRec");
job.getConfiguration().set("mapreduce.job.queuename", "root.Dev");
job.getConfiguration().set("mapreduce.output.textoutputformat.separator","|");
job.setJobName("work_charter_stb.ext_chtr_vod_fyi_mapped");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setJarByClass(charterSelDistRec.class);
job.waitForCompletion(true);
}
}
但是输出文件仍然有复制。请让我知道我错了。
最佳答案
它不必太复杂。您要做的就是:
映射器中的
共享代码:
这是输入:
10001|76884|1995-06-24|1996-06-23 10001|76884|1995-06-24|1996-06-23 10001|75286|1993-06-24|1994-06-24
Here is the code:
public class StackRemoveDup {
public static class MyMapper extends Mapper<LongWritable,Text, Text, NullWritable> {
@Override
public void map(LongWritable ignore, Text value, Context context)
throws java.io.IOException, InterruptedException {
context.write(value,NullWritable.get());
}
}
public static class MyReducer extends Reducer<Text, NullWritable, Text, NullWritable> {
@Override
public void reduce(Text key, Iterable<NullWritable> values, Context context)
throws IOException, InterruptedException {
context.write(key, NullWritable.get());
}
}
public static void main(String[] args)
throws IOException, ClassNotFoundException, InterruptedException {
Job job = new Job();
job.setJarByClass(StackRemoveDup.class);
job.setJobName("StackRemoveDup");
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
job.waitForCompletion(true);
}
}
这是输出:
10001 | 75286 | 1993-06-24 | 1994-06-24
10001 | 76884 | 1995-06-24 | 1996-06-23